app.py

import multiprocessing
import threading
import gradio as gr
from mining import mining
from sts import sts
from utils import getDataFrame, save_to_csv, delete_folder_periodically

CONCURRENCY_LIMIT = 5

with gr.Blocks() as demo:
    with gr.Tab("Paraphrase Mining"):
        with gr.Row():
            gr.Markdown(
                "### Paraphrase mining is the task of finding paraphrases (texts with identical / similar meaning) in a large corpus of sentences")
        with gr.Row():
            with gr.Column():
                gr.Markdown("#### sentences")

                upload_button_sentences = gr.UploadButton(label="upload sentences csv", file_types=['.csv'],
                                                          file_count="single")
                output_data_sentences = gr.Dataframe(headers=["text"], col_count=1, label="sentences data")

                upload_button_sentences.upload(fn=getDataFrame, inputs=upload_button_sentences,
                                               outputs=output_data_sentences, concurrency_limit=CONCURRENCY_LIMIT)

        with gr.Row():
            with gr.Column():
                model = gr.Dropdown(
                    ["Lajavaness/bilingual-embedding-large", "sentence-transformers/all-mpnet-base-v2",
                     "intfloat/multilingual-e5-large-instruct"], label="model", interactive=True)
                score_mining = gr.Number(label="score", value=0.96, interactive=True)
                submit_button_mining = gr.Button("Submit", variant="primary")

        with gr.Row():
            with gr.Column():
                output_mining = gr.Dataframe(headers=["score", "sentence_1", "sentence_2"], type="polars",
                                             label="Mining")

                submit_button_mining.click(
                    fn=mining,
                    inputs=[model, upload_button_sentences, score_mining],
                    outputs=output_mining
                )

                download_button = gr.Button("Download Results as CSV", variant="huggingface")
                download_file = gr.File(label="Downloadable File")

                download_button.click(
                    fn=save_to_csv,
                    inputs=output_mining,
                    outputs=download_file
                )

    with gr.Tab("Semantic Textual Similarity"):
        with gr.Row():  # Row for the title
            gr.Markdown(
                "### Semantic Textual Similarity (STS), we want to produce embeddings for all texts involved and calculate the similarities between them")
        with gr.Row():  # First row of two columns
            with gr.Column():
                gr.Markdown("#### sentences 1")
                upload_button_sentences1 = gr.UploadButton(label="upload sentences 1 csv", file_types=['.csv'],
                                                           file_count="single")
                output_data_sentences1 = gr.Dataframe(headers=["text"], col_count=1, label="sentences 1 data")

                upload_button_sentences1.upload(fn=getDataFrame, inputs=upload_button_sentences1,
                                                outputs=output_data_sentences1, concurrency_limit=CONCURRENCY_LIMIT)

            with gr.Column():
                gr.Markdown("#### sentences 2")
                upload_button_sentences2 = gr.UploadButton(label="upload sentences 2 csv", file_types=['.csv'],
                                                           file_count="single")
                output_data_sentences2 = gr.Dataframe(headers=["text"], col_count=1, label="sentences 2 data")

                upload_button_sentences2.upload(fn=getDataFrame, inputs=upload_button_sentences2,
                                                outputs=output_data_sentences2, concurrency_limit=CONCURRENCY_LIMIT)

        with gr.Row():
            with gr.Column():
                model = gr.Dropdown(
                    ["Lajavaness/bilingual-embedding-large", "sentence-transformers/all-mpnet-base-v2",
                     "intfloat/multilingual-e5-large-instruct"], label="model", interactive=True)
                score_sts = gr.Number(label="score", value=0.96, interactive=True)
                submit_button_sts = gr.Button("Submit", variant="primary")

        with gr.Row():
            with gr.Column():
                gr.Markdown("#### STS Results")

                output_sts = gr.Dataframe(headers=["score", "sentence_1", "sentence_2"], type="polars",
                                          label="Semantic Textual Similarit")

                submit_button_sts.click(
                    fn=sts,
                    inputs=[model, upload_button_sentences1, upload_button_sentences2, score_sts],
                    outputs=output_sts
                )

                download_button = gr.Button("Download Results as CSV", variant="huggingface")
                download_file = gr.File(label="Downloadable File")

                download_button.click(
                    fn=save_to_csv,
                    inputs=output_sts,
                    outputs=download_file
                )

if __name__ == "__main__":
    multiprocessing.set_start_method("spawn")

    folder_path = "data"
    thread = threading.Thread(target=delete_folder_periodically, args=(folder_path, 1800), daemon=True)
    thread.start()

    print(gr.__version__)
    demo.launch()